Have you ever wondered what your pet is saying? We know that sometimes they do certain actions or make a certain noise to indicate how they are feeling, whether they are sick, sad, angry, or hungry, but it’s almost never 100% accurate and most of the time you’ll have to actually spend time with them to get an idea of what they want.However scientists believe that machine learning could be the key to understanding how animals talk. According to a report published in Science Reports (via The Guardian), it seems that researchers who have been studying Egyptian fruit bats have turned to the use of machine learning to find out what exactly the bats are saying to each other.
How this was done was the team spent 75 days continuously monitoring and recording the bats. After which they then tried to separate the bats based on the sounds they made when they argued with each other. After that the information was fed into the computer and a machine learning algorithm was used to correctly identify which bat made which call. So far the researchers are saying that the accuracy of their algorithm is around 71%, with an accuracy of 61% when trying to discern the argument, and 41% accuracy for the eventual outcome.
Speaking to The Guardian, Yossi Yovel, co-author of the study said, “What we find is there are certain pitch differences that characterise the different categories – but it is not as if you can say mating [calls] are high vocalisations and eating are low. We have shown that a big bulk of bat vocalisations that previously were thought to all mean the same thing, something like ‘get out of here!’ actually contain a lot of information.”
Filed in . Read more about AI (Artificial Intelligence) and Science.